1 /* The MIT License
2
3 Copyright (c) 2016-2020 Genome Research Ltd.
4
5 Author: Petr Danecek <pd3@sanger.ac.uk>
6
7 Permission is hereby granted, free of charge, to any person obtaining a copy
8 of this software and associated documentation files (the "Software"), to deal
9 in the Software without restriction, including without limitation the rights
10 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
11 copies of the Software, and to permit persons to whom the Software is
12 furnished to do so, subject to the following conditions:
13
14 The above copyright notice and this permission notice shall be included in
15 all copies or substantial portions of the Software.
16
17 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
18 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
19 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
20 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
21 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
22 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
23 THE SOFTWARE.
24
25 */
26
27 #include <stdio.h>
28 #include <stdlib.h>
29 #include <math.h>
30 #include <string.h>
31 #include <assert.h>
32 #include "dist.h"
33
34 extern void error(const char *format, ...);
35
36 struct _dist_t
37 {
38 uint64_t *bins, nvalues;
39 int nbins;
40 int npow; // the number of orders of magnitude to represent exactly
41 int nexact; // pow(10,npow)
42 int nlevel;
43 };
44
dist_init(int npow)45 dist_t *dist_init(int npow)
46 {
47 dist_t *dist = (dist_t*) calloc(1,sizeof(dist_t));
48 dist->npow = npow;
49 dist->nexact = pow(10,npow);
50 dist->nlevel = dist->nexact - pow(10,npow-1);
51 return dist;
52 }
53
dist_destroy(dist_t * dist)54 void dist_destroy(dist_t *dist)
55 {
56 if ( !dist ) return;
57 free(dist->bins);
58 free(dist);
59 }
60
dist_nbins(dist_t * dist)61 int dist_nbins(dist_t *dist)
62 {
63 return dist->nbins;
64 }
65
dist_nvalues(dist_t * dist)66 int dist_nvalues(dist_t *dist)
67 {
68 return dist->nvalues;
69 }
70
dist_insert(dist_t * dist,uint32_t value)71 uint32_t dist_insert(dist_t *dist, uint32_t value)
72 {
73 int ibin;
74
75 if ( value <= dist->nexact )
76 ibin = value;
77 else
78 {
79 int npow = (int) log10(value);
80 int level = npow - dist->npow + 1;
81 uint32_t step = pow(10, level);
82 ibin = dist->nexact + dist->nlevel*(level-1) + (value - pow(10,npow)) / step;
83 }
84
85 if ( ibin >= dist->nbins )
86 {
87 dist->bins = (uint64_t*) realloc(dist->bins, sizeof(*dist->bins)*(ibin+1));
88 memset(dist->bins + dist->nbins, 0, (ibin+1 - dist->nbins)*sizeof(*dist->bins));
89 dist->nbins = ibin+1;
90 }
91 dist->bins[ibin]++;
92 dist->nvalues++;
93 return ibin;
94 }
dist_insert_n(dist_t * dist,uint32_t value,uint32_t cnt)95 uint32_t dist_insert_n(dist_t *dist, uint32_t value, uint32_t cnt)
96 {
97 if ( !cnt ) return 0;
98 int ibin = dist_insert(dist, value);
99 dist->bins[ibin] += cnt - 1;
100 dist->nvalues += cnt;
101 return ibin;
102 }
103
dist_get(dist_t * dist,uint32_t idx,uint32_t * beg,uint32_t * end)104 uint64_t dist_get(dist_t *dist, uint32_t idx, uint32_t *beg, uint32_t *end)
105 {
106 if ( idx < dist->nexact )
107 {
108 if ( beg ) *beg = idx;
109 if ( end ) *end = idx + 1;
110 }
111 else
112 {
113 int level = (idx - dist->nexact) / dist->nlevel + 1;
114 int bin = idx - dist->nexact - dist->nlevel*(level-1);
115
116 uint32_t step = pow(10, level);
117 uint32_t value = pow(10, level + dist->npow - 1) + step*bin;
118
119 if ( beg ) *beg = value;
120 if ( end ) *end = value + step;
121 }
122 return dist->bins[idx];
123 }
124
125